Commit
·
862921e
1
Parent(s):
400590a
Upload start.ipynb
Browse files- danbooru_cawler/start.ipynb +103 -0
danbooru_cawler/start.ipynb
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cells": [
|
| 3 |
+
{
|
| 4 |
+
"cell_type": "markdown",
|
| 5 |
+
"id": "91225aac-0181-478d-bb6a-2ad7512ec0ca",
|
| 6 |
+
"metadata": {
|
| 7 |
+
"tags": []
|
| 8 |
+
},
|
| 9 |
+
"source": [
|
| 10 |
+
"### 更改设置\n",
|
| 11 |
+
"更改并运行下方单元格"
|
| 12 |
+
]
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"cell_type": "code",
|
| 16 |
+
"execution_count": 13,
|
| 17 |
+
"id": "0c42eb88-737c-4ead-b954-df29809e0076",
|
| 18 |
+
"metadata": {
|
| 19 |
+
"tags": []
|
| 20 |
+
},
|
| 21 |
+
"outputs": [
|
| 22 |
+
{
|
| 23 |
+
"name": "stdout",
|
| 24 |
+
"output_type": "stream",
|
| 25 |
+
"text": [
|
| 26 |
+
"Overwriting danbooru_crawler/settings.py\n"
|
| 27 |
+
]
|
| 28 |
+
}
|
| 29 |
+
],
|
| 30 |
+
"source": [
|
| 31 |
+
"%%writefile danbooru_crawler/settings.py\n",
|
| 32 |
+
"BOT_NAME = \"danbooru_crawler\"\n",
|
| 33 |
+
"SEARCH_TAG = \"cat girl\" # 搜索内容\n",
|
| 34 |
+
"SEARCH_TYPE = 1 # 0 / 1 是否抓取缩略图,0代表抓缩略图,1代表原图\n",
|
| 35 |
+
"SEARCH_LINK = False # True / False 连锁搜索(即搜索子图,训练画风可以打开,训练概念等会出现与tag特征不符的图导致污染训练集)\n",
|
| 36 |
+
"SEARCH_TAG_TXT = True # True / False 是否一并抓取图片自身的tag,推荐打开\n",
|
| 37 |
+
"\n",
|
| 38 |
+
"SPIDER_MODULES = [\"danbooru_crawler.spiders\"]\n",
|
| 39 |
+
"NEWSPIDER_MODULE = \"danbooru_crawler.spiders\"\n",
|
| 40 |
+
"IMAGES_STORE = \"./pics\"\n",
|
| 41 |
+
"ROBOTSTXT_OBEY = False\n",
|
| 42 |
+
"ITEM_PIPELINES = {\n",
|
| 43 |
+
" \"danbooru_crawler.pipelines.PicsDownloadPipeline\": 1,\n",
|
| 44 |
+
" # \"scrapy.pipelines.PicsDownloadPipeline\": 1,\n",
|
| 45 |
+
"}\n",
|
| 46 |
+
"REQUEST_FINGERPRINTER_IMPLEMENTATION = \"2.7\"\n",
|
| 47 |
+
"TWISTED_REACTOR = \"twisted.internet.asyncioreactor.AsyncioSelectorReactor\"\n",
|
| 48 |
+
"FEED_EXPORT_ENCODING = \"utf-8\""
|
| 49 |
+
]
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"cell_type": "markdown",
|
| 53 |
+
"id": "97c71a2b-9474-462e-9910-3fcbea431f53",
|
| 54 |
+
"metadata": {
|
| 55 |
+
"tags": []
|
| 56 |
+
},
|
| 57 |
+
"source": [
|
| 58 |
+
"### 运行"
|
| 59 |
+
]
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"cell_type": "code",
|
| 63 |
+
"execution_count": null,
|
| 64 |
+
"id": "5b398c0d-effe-4891-94cf-2b4148b149bb",
|
| 65 |
+
"metadata": {
|
| 66 |
+
"tags": []
|
| 67 |
+
},
|
| 68 |
+
"outputs": [],
|
| 69 |
+
"source": [
|
| 70 |
+
"!python main.py"
|
| 71 |
+
]
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"cell_type": "code",
|
| 75 |
+
"execution_count": null,
|
| 76 |
+
"id": "35873bfc-8e08-4017-a262-5c61f84fc235",
|
| 77 |
+
"metadata": {},
|
| 78 |
+
"outputs": [],
|
| 79 |
+
"source": []
|
| 80 |
+
}
|
| 81 |
+
],
|
| 82 |
+
"metadata": {
|
| 83 |
+
"kernelspec": {
|
| 84 |
+
"display_name": "Python 3 (ipykernel)",
|
| 85 |
+
"language": "python",
|
| 86 |
+
"name": "python3"
|
| 87 |
+
},
|
| 88 |
+
"language_info": {
|
| 89 |
+
"codemirror_mode": {
|
| 90 |
+
"name": "ipython",
|
| 91 |
+
"version": 3
|
| 92 |
+
},
|
| 93 |
+
"file_extension": ".py",
|
| 94 |
+
"mimetype": "text/x-python",
|
| 95 |
+
"name": "python",
|
| 96 |
+
"nbconvert_exporter": "python",
|
| 97 |
+
"pygments_lexer": "ipython3",
|
| 98 |
+
"version": "3.8.1"
|
| 99 |
+
}
|
| 100 |
+
},
|
| 101 |
+
"nbformat": 4,
|
| 102 |
+
"nbformat_minor": 5
|
| 103 |
+
}
|